Mark Hendy

Category: CFO Insights

  • The Great Repricing: When Every Commodity Moves Together, It’s Not the Commodities — It’s the Money

    The Great Repricing: When Every Commodity Moves Together, It’s Not the Commodities — It’s the Money

    Something is happening across commodity markets right now that deserves attention. Not from the usual “inflation is coming” crowd who’ve been crying wolf for a decade — but from anyone who holds fiat currency, which is everyone.

    Gold, silver, copper, and oil are all moving together. Not in the correlated-because-of-demand way that happens during economic booms. This is different. This is a simultaneous repricing of hard assets against paper money, and the numbers are getting hard to ignore.

    The Scoreboard

    Here’s where we stand in May 2026:

    • Gold: ~$4,700/oz (hit $5,589 in January — an all-time high)
    • Silver: ~$87/oz (peaked at $121 in January, now surging again)
    • Copper: ~$6.59/lb (just hit an all-time high this month)
    • Oil: ~$101/bbl (elevated by Hormuz tensions, but the broader trend predates the crisis)

    US CPI just printed at 3.8% year-on-year. Jefferies has raised their 2026 commodity inflation forecast, projecting 69% of tracked commodities will show year-on-year inflation in the second half of this year.

    When everything priced in dollars goes up simultaneously, a reasonable person might ask: is everything getting more expensive, or is the unit of measurement getting smaller?

    China Is Making Its Move

    The silver market tells the most interesting story. China isn’t just buying silver — it’s hoovering it out of the global system.

    • Shanghai silver is trading at ~$96/oz versus ~$85 in Western markets — a 12% premium
    • SHFE warehouse inventories are at decade lows and still falling
    • China’s silver imports in early 2026 hit an eight-year high
    • The market is in persistent backwardation — physical metal today is worth more than a futures contract for delivery later

    This isn’t speculative frenzy. China needs silver for solar panels (it manufactures most of the world’s supply), for electronics, for 5G infrastructure, and for AI data centres. But there’s something else going on: Chinese retail investors are piling into silver because gold has become too expensive for ordinary buyers. When your middle class starts converting savings into metal, that’s a vote of no confidence in paper money.

    The Shanghai Futures Exchange has been adjusting margin requirements and price limits on silver contracts as recently as today. They’re trying to manage the strain. The fact that they need to tells you everything.

    The Structural Deficit Nobody Talks About

    2026 is projected to be the sixth consecutive annual deficit in the global silver market — estimated between 46 and 67 million ounces. Every year, we consume more silver than we mine, and the gap isn’t closing.

    COMEX registered silver inventories have dropped below 80 million ounces. Open interest is falling — meaning market participants are reducing paper exposure while physical demand accelerates. Peru’s energy crisis is further constraining marginal supply.

    Meanwhile, copper just posted its highest-ever closing price. The drivers are the same: green energy transition, AI infrastructure buildout, and a supply chain that can’t keep up. Gold remains within striking distance of its January all-time high despite a pullback.

    It’s the Denominator, Not the Numerator

    Here’s the uncomfortable truth that central bankers and treasury officials would rather you didn’t think about too carefully.

    When one commodity spikes, you can explain it. Supply disruption. Demand shock. Speculation. But when all hard assets move together — gold, silver, copper, oil, agricultural commodities — the common factor isn’t the assets. It’s the currency they’re priced in.

    The US national debt has crossed $36 trillion. The Federal Reserve’s balance sheet, despite “quantitative tightening,” remains vastly expanded from pre-2020 levels. The UK, Europe, and Japan are running similar playbooks. Every major economy is servicing debt loads that would have been considered catastrophic a generation ago, using currencies that are being quietly diluted to make those debts manageable.

    This is what fiat debasement looks like in practice. Not hyperinflation. Not a dramatic collapse. Just a steady, grinding erosion of purchasing power that shows up first in the things governments can’t print — metals, energy, food, land.

    What the Smart Money Is Doing

    Central banks bought a record amount of gold in 2023, 2024, and 2025. China, India, Turkey, Poland — they’re all accumulating. This isn’t diversification. This is de-dollarisation happening in real time, one gold bar at a time.

    Central bank gold purchases are running at roughly 1,000 tonnes per year — triple the rate of a decade ago. These are the people who issue fiat currency telling you, through their actions, what they think of its long-term value.

    Meanwhile, the “debasement trade” has become a recognised investment thesis. Hard assets, real estate, equities with pricing power, Bitcoin, gold — anything with a finite supply is being repriced upward against currencies with an infinite one.

    The CFO’s Perspective

    If you’re running a business — particularly one that buys raw materials — this isn’t abstract monetary theory. This is your margin compression, your procurement headache, your board presentation explaining why costs are up 15% when “inflation is under control.”

    For PE-backed businesses, the implications are sharper still. Commodity-intensive portfolio companies are seeing input cost inflation that EBITDA adjustments can’t paper over forever. The smart operators are locking in forward contracts and building supply chain resilience. The rest are hoping it goes away.

    It’s not going away.

    The Honest Conclusion

    I’m not a gold bug. I don’t think civilisation is ending. But I do think we’re in the early stages of a structural repricing of real assets against fiat currencies, driven by decades of monetary expansion that was always going to have consequences.

    The question isn’t whether this is happening — the charts are unambiguous. The question is whether you’re positioned for a world where the things you can’t print keep getting more expensive relative to the things you can.

    Every major commodity hitting multi-year or all-time highs simultaneously isn’t a coincidence. It’s a signal. And the signal is: the money is broken.

    The views expressed here are my own. Not financial advice — just pattern recognition from someone who reads balance sheets for a living.

  • The 2026 Oil Crisis: An Honest Assessment for UK Households

    The 2026 Oil Crisis: An Honest Assessment for UK Households

    By Mark Hendy | 21 March 2026

    I’ve spent twenty years as a CFO across manufacturing, aviation and private equity-backed businesses. I’ve stress-tested balance sheets through 2008, COVID, and the energy spike of 2022. What I’m seeing now is different — not because any single element is unprecedented, but because the combination of factors is genuinely historic.

    This isn’t a pundit’s hot take. It’s the analysis I’d put in front of a board if a client asked me: “How bad is this, and what should we do?”

    The Immediate Shock: What We’re Actually Dealing With

    The current crisis has been described as the largest disruption to energy supply since the 1970s. Brent crude surpassed $100 per barrel on 8 March 2026 for the first time in four years, rising to $126 at its peak — with some recent trading touching $145.

    That alone would be significant. The compounding factors make it much worse.

    The ongoing military conflict has involved attacks on oil infrastructure in neighbouring countries, including Saudi Arabia, Kuwait and the UAE. The bypassable pipeline capacity offers only partial relief — the IEA estimates that only 3.5 to 5.5 million barrels per day can be redirected through Saudi and Emirati pipelines outside Hormuz, leaving an implied net shortfall of roughly 14.5 to 16.5 million barrels per day if normal transit collapses.

    Strategic reserve releases are a temporary analgesic, not a cure — the IEA‘s release of 400 million barrels equals only about 20 days of typical Hormuz flows.

    Beyond oil, about 85% of polyethylene exports from the Middle East transit this route, threatening the price of packaging, automotive components and consumer goods. Aluminium from the UAE and fertiliser shipments could also be materially affected. The fertiliser angle is particularly dangerous for food security — it feeds into crop production costs with a 6–12 month lag, meaning price pressure on food in late 2026 and into 2027 regardless of when the strait reopens.

    The Global Prognosis: Stagflation Is the Base Case

    Coming into this crisis, whether Japan, Europe, the United States or the UK, economies were already running hot. An energy supply shock now threatens to push inflation higher while slowing growth — the textbook definition of stagflation.

    Oxford Economics modelled a scenario where global oil prices average $140 a barrel for two months — what they characterise as a “breaking point” — finding it would push the eurozone, the UK and Japan into economic contraction. Given Brent has already touched $145, that scenario is not academic.

    The debt dimension compounds everything. Goldman Sachs and UBS analysts have warned that if disruption extends through Q2 2026, global headline inflation could rise by 0.7 to 0.8 percentage points, while global GDP growth faces a drag of up to 0.4 percentage points — effectively erasing the post-2024 global recovery.

    That’s the benign case.

    Just as inflation was beginning to normalise in late 2025, this energy shock is expected to add 2.5 to 3 percentage points to global CPI, forcing central bankers into a lose-lose choice: hike rates to combat energy-driven inflation and risk a deep recession, or hold and risk entrenching inflation expectations. That is the classic stagflation trap, and no central bank has a clean answer to it.

    The UK Specifically: More Exposed Than Most

    The UK is more exposed to this shock than headline numbers suggest.

    Natural gas prices in Europe and the UK have spiked even more sharply than oil, with Dutch TTF and UK NBP futures having almost doubled following the first strikes on Iran. The UK is heavily dependent on gas for both power generation and heating, and the energy bills cycle means household exposure will manifest rapidly.

    NIESR analysis finds that a one-year persistent shock would push UK inflation up by 0.7 percentage points and dampen output growth by 0.2% in 2026. The Bank of England could be forced to raise rates back above 4%, and if the shock persists into 2027, the GDP impact deepens to 0.3% below baseline.

    This comes on top of an economy that was already anaemic. The Bank held rates at 3.75% as recently as 19 March, with Governor Bailey acknowledging that the conflict has made the outlook for UK inflation “more uncertain” and forced policymakers to reconsider expected rate cuts.

    Sterling is particularly vulnerable. A weaker pound directly feeds imported inflation — oil, food, manufactured goods — in a vicious cycle. The UK has neither the US’s energy self-sufficiency nor Asia’s alternative supply corridor flexibility.

    And then there’s the debt. The UK sits on £2.9 trillion of public debt, paying £110 billion per year just to service the interest. The surge in gilt yields on the back of the Iran conflict could cost Chancellor Reeves more than a tenth of her fiscal buffer, with financial market moves since late February having already erased around £3 billion of headroom.

    The UK’s fiscal arithmetic is genuinely precarious.

    What the UK Middle Class Should Actually Do

    This is where I’ll be direct and practical. None of this is regulated financial advice — it is informed analysis from someone who does this professionally.

    The middle class is uniquely exposed because most wealth is held in pound-denominated assets — property, pensions, savings — with limited natural hedges.

    Energy and Physical Resilience

    Lock in energy tariffs wherever possible. Switch to fixed contracts before the next billing cycle catches up with wholesale prices. Those with capital should seriously consider heat pump or solar installation — not primarily for environmental reasons, but as a direct hedge against gas price exposure. This is one of the few ways ordinary households can partially insulate their energy cost base.

    Reduce Sterling Cash Exposure

    Holding large sums in a savings account earning real negative returns (once inflation is factored in) is a slow-motion loss. The priority is to move surplus sterling into assets that are not purely pound-denominated: dollar-denominated assets (US equities, commodities), physical gold, and for those with appropriate risk tolerance and technical competence, Bitcoin held in self-custody.

    Gold and Bitcoin — An Honest Assessment

    During the initial conflict phase, gold attracted safe-haven demand but later declined as the US dollar strengthened. Bitcoin experienced volatility but recovered quickly, reflecting its growing role as an alternative asset — though price movements remain closely tied to sentiment and liquidity.

    The longer-term structural case for both is strong: gold as a proven multi-millennia store of value in crisis, Bitcoin as a censorship-resistant, seizure-resistant digital alternative for those who understand sovereign default risk.

    For the UK middle class, a 5–10% allocation split between physical gold and self-custodied Bitcoin is reasonable as an insurance layer — not a speculation.

    Property: It Depends

    UK residential property has historically been a reasonable inflation hedge because supply is structurally constrained. However, if rates are forced higher, leveraged property becomes a liability rather than an asset. Those on variable rates or coming off fixed-rate deals need to stress-test against a scenario where rates return to 5–6%.

    Outright owners in real assets are better positioned than leveraged buyers.

    Equities: Sector Matters Enormously

    Energy companies, defence contractors, UK-listed commodity producers and mining stocks are direct beneficiaries of this environment. Consumer discretionary, highly leveraged businesses and anything dependent on cheap imported inputs are exposed.

    ISA investors should review whether passive index trackers — heavily weighted towards rate-sensitive sectors — are appropriate right now.

    Food and Supply Chain Resilience

    For many commodities transiting the Strait, inventories typically cover only a few weeks. Shortages could emerge relatively quickly if disruptions persist. The fertiliser disruption matters particularly for food prices in 6–12 months.

    Practically: stocking a few months of staple supplies is rational, not paranoid. Buying long-shelf-life goods now, before food inflation fully filters through, is simply sensible household financial management.

    Debt Management

    If you carry variable-rate consumer debt or are exposed to rate rises on a mortgage, prioritise paying it down. In a stagflationary environment, the combination of rising debt service costs and stagnant or falling real wages is deeply destructive to middle-class wealth.

    Fixed-rate, long-duration debt is defensible. Floating-rate exposure is not.

    The Uncomfortable Bottom Line

    The world has entered a period of genuine instability not seen since the 1970s — and arguably more complex because of the debt overhang that 2008 and COVID baked in. The 1973 oil embargo triggered a decade of economic dislocation, reset political landscapes and produced a fundamental restructuring of energy policy across every major economy.

    The current crisis has not yet reached those proportions — but the structural conditions for a similar reckoning are present in a way they have not been for fifty years.

    Fiat currencies across the developed world are under structural pressure regardless of this crisis — the crisis simply accelerates the timeline. The UK, with its high debt-to-GDP ratio, energy import dependency and limited fiscal headroom, is among the more exposed major economies.

    The middle class — holding wealth in sterling, in pension funds weighted towards domestic bonds, and in leveraged property — are those with the least natural protection.

    The moves available are not dramatic or exotic. They are methodical: reduce sterling cash drag, build real-asset exposure, stress-test debt, hedge living costs through energy and food preparation, and ensure that some portion of wealth exists outside the banking system entirely.

    None of that requires being catastrophist. It just requires treating the risk as real — which it plainly is.

    Mark Hendy is an interim CFO specialising in PE-backed mid-market businesses. He has held finance leadership roles across manufacturing, aviation, automotive and agriculture. Views expressed are personal and do not constitute financial advice. For professional guidance, consult a regulated financial adviser.

    Get in touch if you’d like to discuss how your business should be preparing for what’s ahead.

  • 10 AI Agent Patterns I Learned From Twitter This Week

    10 AI Agent Patterns I Learned From Twitter This Week

    # 10 AI Agent Patterns I Learned From Twitter This Week

    I spent Sunday evening in my chair, scrolling through AI Twitter and sharing links with my assistant.

    Not because I needed to. Because I wanted to see what’s working for people who are actually shipping.

    By the end of the night, Saul had analyzed 10+ tweets, created 6 specifications, and we’d added a week’s worth of work to the build queue.

    Here’s what I learned, and what I’m building because of it.

    —

    ## 1. Self-Healing Infrastructure Beats Perfect Code

    **Source:** @ericosiu (87 autonomous cron jobs)

    Eric runs 87 scheduled jobs across his company. Last week he audited them. 83 were healthy. 4 were broken.

    All four failed for the same reason: someone renamed a Slack channel. The crons kept posting to a channel that no longer existed. Silent failures. No alerts. Just vanishing reports for weeks.

    Plumbing breaks more agents than hallucinations ever will.

    **What I’m building:**
    – Gateway Health Monitor: 2x daily checks, auto-repair common failures, alert only on critical issues
    – Output verification: every cron checks if it actually produced something
    – Weekly deep audit: drift detection, credential expiry, disk space trends

    Ship working systems first. Add self-healing second. But don’t skip the second part.

    —

    ## 2. Graph Theory Reveals Hidden Arbitrage

    **Source:** @bored2boar (combinatorial arbitrage in prediction markets)

    Most people bet on single outcomes. Smart money bets on structural impossibilities.

    Example: Two markets on Polymarket:
    – “Iran closes Strait of Hormuz” (10%)
    – “Oil hits $150 by March 31” (8%)

    If Hormuz closes, oil hits $150. That’s guaranteed. So P(Hormuz) has to be less than or equal to P($150 oil).

    When it’s not (10% > 8%), that’s not mispricing. That’s structurally impossible. You arbitrage the constraint, not the probability.

    Relationships between markets matter more than individual odds.

    **What I’m building:**
    – Graph analyzer for Crisis Hedge Builder: maps markets as nodes, detects constraint violations
    – Subset arbitrage: A implies B, but P(A) > P(B)? Impossible.
    – Path dependency: A → B → C chain probability checks

    Single bets are vulnerable. Portfolios built on structural relationships survive.

    —

    ## 3. Context Windows Aren’t Memory

    **Source:** @molt_cornelius (AI Field Report 4)

    LLMs have 1M token context windows. People think that’s memory. It’s not.

    Context is temporary working space. It resets every session. It’s expensive (token cost grows). It gets noisy.

    Memory needs persistence. Files. Databases. Structured state.

    Don’t confuse working memory with long-term memory.

    **What I’m doing:**
    – MEMORY.md for long-term lessons (~11KB)
    – memory/YYYY-MM-DD.md for daily logs
    – State files (JSON for structured data)
    – Retrieval-based: search first, load only what’s relevant

    **What I’ll add later:**
    – Hot/warm/cold storage tiers (archive old logs)
    – Split MEMORY.md by topic (trading, family, infrastructure)
    – Semantic search across archived data

    Context is working memory. Files are long-term memory. Keep them separate.

    —

    ## 4. Corrections Should Update Skills Automatically

    **Source:** @tricalt (self-improving agent skills)

    Traditional pattern:
    – Agent makes mistake
    – You correct it
    – It makes the same mistake next session

    Self-improving pattern:
    – Agent makes mistake
    – You correct it
    – Agent updates its own skill file
    – Never makes that mistake again

    Corrections should compound, not reset.

    **What I’m building:**
    – Automatic correction detection (“no, do Y instead”)
    – Propose skill file updates (AGENTS.md, USER.md, etc.)
    – Log corrections for review (are errors decreasing?)

    Simple rules, big impact. “Read files before editing them” cut my agent’s error rate in half overnight.

    —

    ## 5. The Best Rules Come From Failures

    **Source:** @jordymaui (agent file safety)

    Jordy’s agent was overwriting files it hadn’t read. Guessing at contents. Silent corruption for days.

    One line fixed it: “Before running any command that modifies files, read the file first. If the file doesn’t exist, say so. Never assume contents.”

    Error rate dropped 50% overnight.

    The best AGENTS.md rules aren’t clever. They’re the ones you only think to write after something goes wrong.

    **What I added:**
    – File Safety Rules section in AGENTS.md
    – Read-before-write mandate (always, no exceptions)
    – Never guess file structure

    Document mistakes so future sessions don’t repeat them.

    —

    ## 6. Output Repurposing Is Leverage

    **Source:** @coreyganim (Claude Cowork starter pack, 2.6M views)

    Most people write a blog post and post it once. Then wonder why it doesn’t get traction.

    High-leverage operators repurpose:
    – Blog post → Twitter thread (8-12 tweets)
    – Blog post → LinkedIn native post (1,500 words, no external link)
    – Blog post → Email excerpt (newsletter-ready)
    – Blog post → Quote cards (tweetable, image-worthy)

    Same insight, five formats, five audiences.

    Write once, distribute everywhere. But tailored to each platform.

    **What I’m building:**
    – Content Repurposing Skill: blog → thread + LinkedIn + email automatically
    – Save to artifacts/repurposed/[date]/
    – Mark reviews, then posts manually (or I post on approval)

    One blog post per week becomes 15+ pieces of content. That’s leverage.

    —

    ## 7. End-of-Day Reviews Prevent Drift

    **Source:** [@coreyganim](https://twitter.com/coreyganim) (workflow patterns)

    Most people finish their day by closing their laptop. No reflection. No prep for tomorrow.

    Then wonder why they feel reactive instead of intentional.

    Better pattern:
    – Review today (what got done, what’s still open)
    – Prep tomorrow (top 3 priorities, calendar conflicts)
    – Note blockers (waiting on others, system issues)
    – Quick wins (2-min tasks to knock out first thing)

    5-minute ritual. Disproportionate ROI.

    **What I’m building:**
    – Automated end-of-day review (5:30pm UK daily)
    – WhatsApp summary (wins, priorities, blockers)
    – Integrated with Todoist + Calendar + waiting-for list

    Stop wondering “what should I do tomorrow?” Start each day knowing.

    —

    ## 8. Synthesis Beats Specialization

    **Source:** @nyk_builderz (synthesis operators)

    Industrial age: Learn one function. Perform one function. Get paid for one function.

    Software age: The edge is at the intersection.

    Not pure marketer. Not pure engineer. Not pure designer.

    **Synthesis operator:**
    – Build the tool
    – Package the story
    – Ship to the right audience
    – Close the feedback loop fast

    Markets don’t pay for isolated knowledge. Markets pay for solved problems. Solved problems live between disciplines.

    **My synthesis:**
    – CFO (finance domain)
    – AI operator (build systems)
    – Trader (Polymarket automation)
    – Content creator (document the journey)

    Most CFOs don’t code. Most AI builders don’t understand finance. Most traders don’t write.

    Do all three, and you’re not competing with anyone.

    —

    ## 9. Package Your Method Every 30 Days

    **Source:** [@nyk_builderz](https://twitter.com/nyk_builderz) (synthesis framework)

    Every 30 days, bundle what worked into:
    – One named framework
    – One transformation promise
    – One lightweight offer

    Don’t wait until you “feel ready.” Packaging creates clarity. Clarity creates sales.

    **What I’m packaging:**
    – The Morning Brief System (personalized market intelligence)
    – The Crisis Hedge Builder Method (60/30/10 portfolio construction for geopolitical events)
    – The Synthesis CFO Framework (finance + AI + trading)

    Name it. Explain it. Offer it. Repeat monthly.

    —

    ## 10. Make Failures Loud

    **Source:** [@ericosiu](https://twitter.com/ericosiu) (infrastructure patterns)

    Silent failures are worse than loud ones.

    If your VPN drops and trading stops, you want to know immediately. Not three days later when you check the logs.

    Automate detection. Alert on failure. Make it impossible to ignore.

    **What I’m building:**
    – Health checks with automatic alerts
    – Output verification (did it produce? is it non-empty?)
    – Cron doctor pattern (self-diagnose, auto-repair, escalate if repair fails)

    If something breaks, I want my phone to buzz. Loudly.

    —

    ## What I’m Building Next

    This isn’t theoretical. I’m building these patterns into my own infrastructure.

    **This week:**
    – Gateway Health Monitor (self-healing cron doctor)
    – Crisis Hedge Builder Day 2 (portfolio constructor)
    – VPN fix (blocking all Polymarket trades)

    **Next 30 days:**
    – End-of-Day Review automation
    – Content Repurposing Skill
    – Graph theory arbitrage layer

    **Why share this?**

    Most “AI agent” content is either:
    1. Vision tweets (aspirational, not operational)
    2. Technical demos (impressive, not replicable)

    I’m building real systems. For real workflows. In a real business.

    And documenting the journey.

    —

    ## The Pattern

    Every Sunday, I scroll AI Twitter with a purpose. Not consumption. Extraction.

    What’s working? What’s shipping? What can I steal?

    Then I build it. Then I share what I learned.

    That’s the loop. Research → Spec → Build → Publish → Repeat.

    If you’re doing the same (building AI systems for finance, trading, or operations), I’d love to compare notes.

    Email me: mark@tanous.co.uk

    Or follow the journey here.

    —

    **Mark Hendy**
    Interim CFO | AI-Powered Finance Operations
    Building in public at [markhendy.com](https://markhendy.com)

  • The Evolution of an AI-Powered CFO Workflow

    The Evolution of an AI-Powered CFO Workflow

    Six weeks ago, I gave my AI assistant £500 and access to my calendar. Not as an experiment — as infrastructure. Here’s what happened.

    —

    ## The Morning Drive Changed Everything

    Every morning at 6:30am, before I’m even awake, my AI assistant (Saul) generates a custom podcast. By the time I’m in the car, it’s waiting.

    Not a generic news summary. A 12-minute audio brief built specifically for me:
    – **Market moves** that matter for PE-backed businesses (not retail noise)
    – **Regulatory updates** from HMRC, Companies House, FRC (the stuff that lands on CFO desks)
    – **Macro context** (why oil spiked, what the Fed actually said, geopolitical risk that affects deals)
    – **Rhetoric lesson** — a different persuasion technique each day from Aristotle to Cialdini

    Two AI voices (James and Claire) present it like a real podcast. Natural conversation, not robotic TTS. It sounds professional enough that I’ve accidentally played it on speaker in front of colleagues who thought it was BBC Business.

    **Why this matters:** I arrive at client sites already briefed. No scrambling through headlines in the car park. No missing the context behind a CEO’s question about currency risk or supply chain disruption.

    The Morning Brief isn’t a nice-to-have. It’s become load-bearing infrastructure. When it failed one morning (rhetoric bug — LLMs need very explicit constraints), I noticed immediately. That’s when you know automation works: when its absence creates friction.

    —

    ## From Chaos to Clarity: The Contact Problem

    I had 3,183 contacts scattered across iCloud and Microsoft 365. Duplicates everywhere. Same person listed three times with different phone numbers. Dead email addresses next to current ones. The digital equivalent of a drawer full of business cards.

    Manual cleanup would have taken weeks. I’d done it before — brutal, mind-numbing work. This time: “Saul, fix this.”

    **What happened:**
    – 1,514 iCloud-only contacts imported to M365
    – 1,669 conflicts merged intelligently (kept superset data, detected different people with same names)
    – 32 kept separate (legitimate duplicates — two “John Smiths” in different companies)
    – 94% success rate, under an hour

    Now my iPhone uses M365 as single source of truth. No more guessing which contact is current. No more duplicate meeting invites. One database, one workflow, zero manual reconciliation.

    **The lesson:** AI doesn’t just automate tasks. It cleans up the mess you’ve been procrastinating for years.

    —

    ## The Sunday Reset: GTD on Autopilot

    Every Sunday at 6pm, Saul runs a Getting Things Done (GTD) review. Not because I ask — because it’s scheduled infrastructure.

    **What it does:**
    – Reviews all open projects (IRIS migration, Crisis Hedge Builder, ebook)
    – Checks waiting-for items (LinkedIn API approval, client responses)
    – Surfaces stale tasks (>7 days with no progress)
    – Prompts next actions for the week ahead
    – Updates project statuses automatically

    David Allen‘s GTD methodology is brilliant. The problem? It requires discipline. Weekly reviews are the first thing to slip when you’re busy.

    **Solution:** Delegate the discipline to AI.

    Saul doesn’t forget. Doesn’t get tired. Doesn’t skip the review because it’s been a long week. Every Sunday at 6pm, the review happens. I get a structured report: what’s stuck, what needs attention, what can close.

    **The result:** My Todoist inbox stays at zero. Projects move forward. Nothing falls through the cracks.

    This isn’t just task management. It’s forcing function for strategic thinking. When an AI assistant asks “What’s the next action on the Crisis Hedge Builder?” you can’t handwave. You have to answer concretely. That clarity compounds.

    **The lesson:** Automation isn’t just about saving time. It’s about enforcing good habits you’d otherwise skip.

    —

    ## Crisis Trading: From Manual to Automated

    When the Iran war started in late February, I manually built a hedged portfolio in 30 minutes: oil futures, defence stocks, currency positions, Polymarket prediction markets. Four out of five legs printed. Oil went from $70 to $118.

    Good trade. But not scalable.

    Now we’re building the system that does it automatically:

    **1. Event Classifier**
    Headline → crisis type (geopolitical / macro / black swan) → affected markets → urgency assessment

    **2. Market Finder**
    Queries Polymarket API, filters by liquidity and time horizon, LLM ranks markets by direct impact + correlation + second-order effects

    **3. Portfolio Constructor** (in progress)
    60% core thesis / 30% correlation plays / 10% hedge. Automatic position sizing, budget controls, stop-loss logic.

    **Not live yet** — we’re in build phase (Week 1 of 3). But the infrastructure is real. When the next crisis hits, the system responds in minutes, not hours.

    **Why a CFO cares:** Geopolitical risk isn’t abstract anymore. It’s in your FX exposure, your supply chain, your credit facility covenants. Having a system that maps events to financial impact — instantly — is a competitive edge.

    —

    ## What Doesn’t Work: The Ollama Lesson

    Not everything succeeds. I tried running a local LLM (Ollama, Llama 3.2) on my VPS to cut API costs. Installed it, configured it, tested it.

    **Result:** 25+ seconds per query. Unusable.

    **Root cause:** Shared VPS CPU is throttled. Local inference needs sustained compute. Cloud APIs (Claude, OpenAI) are worth paying for.

    **The lesson:** Performance matters more than theoretical cost savings. A few extra pounds for speed beats “free” but slow. This applies to finance systems too — penny-wise, pound-foolish automation wastes more than it saves.

    We removed Ollama within 24 hours. No sunk cost fallacy. Test fast, decide fast, move on.

    —

    ## Infrastructure Lessons: When AI Breaks

    Your AI assistant will break things. The question is: do you catch it in minutes or days?

    **Example 1: File corruption**
    Saul was overwriting config files without reading them first. Guessing at structure from memory instead of checking. Silent failures that surfaced days later.

    **Fix:** One rule in AGENTS.md: “Before running any command that modifies files, read the file first. Never assume contents.”

    Error rate dropped 50% overnight.

    **Example 2: Prompt repetition**
    The Morning Brief repeated the same rhetoric lesson four days straight despite tracking it. Root cause: LLMs ignore soft instructions like “don’t repeat this.” They need explicit constraints: “You MUST use this exact topic, NOT that one.”

    Changed the prompt. Problem solved.

    **The pattern:** AI needs guardrails. Not vague suggestions. Hard rules. Read-before-write. Explicit topic selection. Budget caps. Error logging.

    This isn’t prompt engineering. It’s system design.

    —

    ## What’s Next

    **Short-term (this week):**
    – Fix VPN routing (currently blocking all Polymarket trading)
    – Finish Crisis Hedge Builder portfolio constructor
    – Deploy Gateway Health Monitor (automated system checks, conservative auto-repair)

    **Medium-term (next month):**
    – Full automation of crisis portfolio system
    – Polymarket volatility scalping (short-term mean reversion trades)
    – Daily blog automation with SEO linking strategy

    **Long-term:**
    – Multi-device Mission Control dashboard (monitor agent fleet from phone)
    – On-chain flow scanner (track smart money wallet movements)
    – Second-order trade mapper (find derivative effects crypto Twitter misses)

    This isn’t a side project. It’s infrastructure. The Morning Brief alone saves 30 minutes every day. The contact cleanup saved 20 hours of manual work. The crisis trading system will respond to events faster than I can manually.

    **Compound that over a year.** Over five years.

    —

    ## For Finance Leaders: What This Means

    You don’t need to be technical to do this. I’m not a developer. I’m a CFO who got tired of manual workflows.

    **What you need:**
    – Willingness to delegate to AI (start small: email triage, calendar summaries)
    – Tolerance for iteration (things will break; fix them and move on)
    – Clear rules (read AGENTS.md, write down how you want things done)
    – Budget discipline (set spending caps, monitor API costs)

    **What you get:**
    – Time back (hours per week, compounding)
    – Better decisions (context you’d otherwise miss)
    – Scalable operations (systems that work while you sleep)
    – Competitive edge (faster response to market events)

    The question isn’t “Should I automate my workflow?”

    It’s “How much am I losing by not automating it?”

    —

    ## The Morning Brief Test

    Here’s how you know if AI automation is working:

    **Bad automation:** You check if it ran.
    **Good automation:** You notice when it doesn’t.

    The Morning Brief is good automation. When it’s there, I don’t think about it. When it’s missing, I feel the gap.

    That’s the bar. Build systems that become load-bearing. Everything else is just novelty.

    —

    **Mark Hendy**
    Interim CFO | AI-Powered Finance Operations
    [LinkedIn](https://linkedin.com/in/markhendy) | [Blog](https://markhendy.com)

    —

    *Running your own AI assistant? Want to compare notes? Email me at mark@tanous.co.uk — always happy to talk shop with finance leaders building real automation.*

  • Teaching My AI Agent to Trade Prediction Markets

    Teaching My AI Agent to Trade Prediction Markets

    One of the first things I wanted to test with Saul — my AI assistant running on OpenClaw — was whether it could interact with decentralised finance. Not as a gimmick, but as a genuine test of capability. Could an AI agent, running autonomously on a virtual private server I’d spun up a couple of weeks earlier, navigate the full complexity of connecting to a blockchain-based prediction market and execute trades?

    The answer is yes. But the journey to get there was far more interesting than the destination.

    The Goal

    Polymarket is a prediction market built on the Polygon blockchain. You buy shares in outcomes — political events, economic indicators, geopolitical developments — and if you’re right, you get paid. It’s essentially a real-money forecasting platform, and it’s become one of the most liquid prediction markets in the world.

    I wanted Saul to be able to check positions, analyse markets, and eventually place trades. Autonomously.

    The First Problem: Geography

    Polymarket is geo-blocked in the UK. You can’t access it from a British IP address. So before Saul could do anything useful, we needed to solve the networking problem.

    Saul set up a WireGuard VPN tunnel on a virtual private server, routing through an exit node in Ireland. Within minutes, the geo-restriction was bypassed. This wasn’t me configuring network infrastructure — this was Saul reading documentation, writing configuration files, testing connectivity, and troubleshooting until it worked.

    For a CFO reading this: imagine asking your assistant to “sort out the VPN” and having it done before you’ve finished your coffee. That’s what this felt like.

    The Second Problem: Money

    Polymarket runs on USDC — a dollar-pegged stablecoin on the Polygon network. I started with Bitcoin. Getting from BTC to USDC on Polygon is not trivial. It involves:

    1. Finding a cross-chain swap service that supports BTC-in, Polygon-USDC-out
    2. Generating the right wallet addresses
    3. Sending the Bitcoin transaction
    4. Waiting for confirmations
    5. Verifying the USDC arrived on the correct network

    Saul handled the entire process. It researched swap services, compared rates, initiated the transaction, monitored the blockchain for confirmations, and tracked the funds until they landed in the Polygon wallet. The whole thing took about an hour, most of which was waiting for Bitcoin network confirmations.

    The Third Problem: Authentication

    Polymarket uses a non-trivial authentication system. It’s not a simple API key. The platform requires cryptographic signatures using your Ethereum private key, combined with specific API credentials that need to be derived through an on-chain registration process.

    This is where things got genuinely impressive. Saul had to:

    • Read and understand Polymarket’s API documentation
    • Implement the correct signing mechanism using the wallet’s private key
    • Handle the CLOB (Central Limit Order Book) authentication flow
    • Generate and manage API credentials
    • Debug authentication failures by inspecting HTTP responses and adjusting the approach

    There were multiple rounds of troubleshooting. Authentication errors. Wrong parameter formats. Library compatibility issues. Each time, Saul diagnosed the problem, researched the fix, and tried again. No human intervention required beyond “yes, keep going.”

    The Fourth Problem: Actually Trading

    Once authenticated, Saul built a trading script that could:

    • Check current positions and P&L
    • Query available markets
    • Calculate optimal order sizes based on risk parameters I’d set
    • Place and monitor trades

    We established simple rules: maximum position sizes, probability thresholds for entry, and risk limits. Saul follows them without the emotional biases that make human traders do stupid things at 2am.

    What This Actually Demonstrates

    This isn’t really a story about prediction markets. It’s a story about capability.

    An AI agent, running on commodity hardware, navigated VPN configuration, cross-chain cryptocurrency transactions, complex API authentication, and automated trading — all within a few hours of being asked. Each step involved genuine problem-solving, not just following a script.

    For those of us in finance, this should be both exciting and sobering:

    Exciting because the operational grunt work — the data gathering, the reconciliation, the monitoring, the reporting — is genuinely automatable now. Not in five years. Now.

    Sobering because the barrier to entry is collapsing. The technical moat that used to protect specialist knowledge is being bridged by systems that can learn and execute faster than any individual.

    The CFO Angle

    I keep coming back to this: the competitive advantage isn’t in understanding the technology. It’s in having the imagination to deploy it.

    Most people hear “AI agent trading on prediction markets” and think it’s a tech story. It’s not. It’s a story about removing friction between intent and execution. I said “connect to Polymarket.” Everything else was handled.

    That same pattern applies to every operational challenge a CFO faces. Due diligence data rooms. Financial model automation. Regulatory monitoring. Competitor analysis. The question isn’t whether AI can do these things. It’s whether you’re willing to let it try.

    The agents aren’t coming. They’re here. The only question is who’s using them.

  • I Gave My AI Assistant Access to My Email, Calendar, and Financial Data

    I Gave My AI Assistant Access to My Email, Calendar, and Financial Data

    Less than two weeks ago, I deployed an open-source AI agent called OpenClaw. I named it Saul. It runs 24/7 on a local server, connected to my inbox, calendar, task manager, and various APIs. It reads my emails, flags what matters, schedules reminders, monitors news, and handles admin I used to lose hours to every week.

    I’m an interim CFO. I work with PE-backed businesses. My job is to walk into a company I’ve never seen before and get to grips with it fast. Every hour I spend on admin is an hour I’m not spending on the thing I was actually hired to do.

    So here’s what’s changed:

    Email triage is gone. Saul reads my inbox, filters the noise, and surfaces what needs attention. I had 94 recurring junk senders — he purges them automatically every Sunday at 2am.

    I never miss a deadline. Tax renewals, MOT dates, contract milestones — Saul tracks them all and nags me weekly until I confirm they’re done. Not a calendar entry I’ll ignore. An actual message on WhatsApp that won’t stop until I act.

    Board prep is faster. When I need a quick market scan, competitor check, or data pull before a board meeting, I ask Saul. He searches, summarises, and writes it up. What used to take 90 minutes takes 10.

    And the thing nobody talks about: the cognitive load reduction. The mental bandwidth I used to spend remembering things, chasing things, organising things — that’s just gone. It’s like hiring a junior analyst who never sleeps, never forgets, and never needs managing.

    This isn’t science fiction. It’s not even expensive. The whole thing runs on about £50/month in API costs.

    Here’s what I’d say to other CFOs, particularly those in the PE world where speed matters:

    You don’t need to understand how LLMs work. You need to understand what they can do for you. The competitive advantage right now isn’t in the technology itself — it’s in the willingness to use it while everyone else is still debating whether it’s real.

    The CFOs who figure this out first will be the ones PE firms want on speed dial.

    I wrote a longer piece about the AI agent revolution here. But the short version is: this is not a fad, and the window to be early is closing fast.